krafton-ai
- 15 skills
- 0 followers
- 14 hours ago last updated
- ▌ Add Tts Model · krafton-ai bundleIntegrate a new text-to-speech model into vLLM-Omni from HuggingFace reference implementation through production-ready serving with streaming and CUDA graph acceleration. Use when adding a new TTS model, wiring stage separation for speech synthesis, enabling online voice generation serving, debugging TTS integration behavior, or building audio output pipelines.
- ▌ Add Diffusion Model · krafton-ai bundleAdd a new diffusion model (text-to-image, text-to-video, image-to-video, text-to-audio, image editing) to vLLM-Omni, including Cache-DiT acceleration and parallelism support (TP, SP/USP, CFG-Parallel, HSDP). Use when integrating a new diffusion model, porting a diffusers pipeline or a custom model repo to vllm-omni, creating a new DiT transformer adapter, adding diffusion model support, or enabling multi-GPU parallelism and cache acceleration for an existing model.
- ▌ Vllm Omni Npu Model Runner Upgrade · krafton-ai bundleUpgrade vllm-omni NPU model runners (OmniNPUModelRunner, NPUARModelRunner, NPUGenerationModelRunner) to align with the latest vllm-ascend NPUModelRunner while preserving omni-specific logic.
- ▌
- ▌
- ▌ Meta Harness Chess Puzzle · krafton-aiEvolve prompt/parser/observation/retry harnesses for chess-puzzle-v0 without solving chess inside the harness.
- ▌ PDF · krafton-ai bundleComprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
- ▌ Channel Setup · krafton-aiUse when the user asks how to connect or configure Slack, Telegram, or Discord in KiraClaw, including which token or settings field to fill in, what platform-side setup is required, and when an engine restart is needed.
- ▌ Skill Creator · krafton-aiCreate or refine KiraClaw/Codex skills as concise SKILL.md packages. Trigger on: "make a skill", "create a skill", "update this skill", "seed skill", "default skill", or when the user wants reusable agent workflow instructions instead of one-off prompt text.
- ▌ Speak Natural · krafton-aiMake channel-facing speak output sound natural and easy to read. Trigger on: preparing a Slack, Telegram, or Discord reply with speak; rewriting markdown-heavy or AI-sounding prose before delivery; or when a response feels too formal, too structured, or too obviously model-written for a chat conversation.
- ▌ Playwright Use · krafton-aiPractical browser automation guidance for KiraClaw browser MCP tasks. Trigger on: opening a downloaded HTML file, testing a localhost app, validating a web flow in the browser, interacting with a browser game, or when Playwright/browser actions keep timing out or failing.
- ▌ HTML Presentation · krafton-ai bundleCreate polished single-file HTML presentations matching the ARIA design system. Trigger on: "create a presentation", "make slides", "build a slide deck", "HTML presentation", or when the user wants to present information visually as a slide deck.
- ▌ Slack Memory Store · krafton-ai bundleComprehensive memory storage system for AI employees in IT companies who communicate via Slack. Automatically classifies and stores diverse information types (Slack messages, Confluence docs, emails, meetings, projects, decisions, feedback) in an organized folder structure with efficient indexing and retrieval. Use when managing or searching employee memory, storing conversations, documenting decisions, tracking projects, or organizing any work-related information.
- ▌ Slack Memory Cleanup · krafton-ai bundleMemory cleanup and organization skill for AI employees. Provides guidelines for detecting duplicates, fixing misclassified files, and removing stale information from memory storage.
- ▌ Slack Memory Retrieval · krafton-ai bundleRetrieve and utilize stored memories for AI employees in Slack environments. Efficiently searches and loads relevant context (channels, users, projects, decisions, meetings) from organized memory storage to inform responses. Use this when answering questions that require historical context, user preferences, project status, or any previously stored information. Works with slack-memory-store storage system.